CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Improving Multi-Atlas Segmentation Methods for Medical Images

Jennifer Alvén (Institutionen för elektroteknik, Bildanalys och datorseende)
Gothenburg : Chalmers University of Technology, 2017.

Semantic segmentation of organs or tissues, i.e. delineating anatomically or physiologically meaningful boundaries, is an essential task in medical image analysis. One particular class of automatic segmentation algorithms has proved to excel at a diverse set of medical applications, namely multi-atlas segmentation. However, these multi-atlas methods exhibit several issues recognized in the literature. Firstly, multi-atlas segmentation requires several computationally expensive image registrations. In addition, the registration procedure needs to be executed with a high accuracy in order to enable competitive segmentation results. Secondly, up-to-date multi-atlas frameworks require large sets of labelled data to model all possible anatomical variations. Unfortunately, acquisition of manually annotated medical data is time-consuming which needless to say limits the applicability. Finally, standard multi-atlas approaches pose no explicit constraints on the output shape and thus allow for implausibly segmented anatomies.

This thesis includes four papers addressing the difficulties associated with multi-atlas segmentation in several ways; by speeding up and increasing the accuracy of feature-based registration methods, by incorporating explicit shape models into the label fusion framework using robust optimization techniques and by refining the solutions with means of machine learning algorithms, such as random decision forests and convolutional neural networks, taking both performance and data-efficiency into account. The proposed improvements are evaluated on three medical segmentation tasks with vastly different characteristics; pericardium segmentation in cardiac CTA images, region parcellation in brain MRI and multi-organ segmentation in whole-body CT images. Extensive experimental comparisons to previously published methods show promising results on par or better than state-of-the-art as of date.

Nyckelord: random decision forests, multi-atlas segmentation, conditional random fields, convolutional neural networks,Supervised learning, feature-based registration, medical image segmentation, image registration, label fusion, semantic segmentation

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2017-08-14. Senast ändrad 2017-08-28.
CPL Pubid: 251100


Läs direkt!

Lokal fulltext (fritt tillgänglig)

Institutioner (Chalmers)

Institutionen för elektroteknik, Bildanalys och datorseende


Informations- och kommunikationsteknik
Datorseende och robotik (autonoma system)
Medicinsk bildbehandling

Chalmers infrastruktur

Relaterade publikationer

Inkluderade delarbeten:

Good Features for Reliable Registration in Multi-Atlas Segmentation

Überatlas: Robust Speed-Up of Feature-Based Registration and Multi-Atlas Segmentation

Überatlas: Fast and robust registration for multi-atlas segmentation

Automatic pericardium segmentation and quantification of epicardial fat from computed tomography angiography

Shape-aware multi-atlas segmentation


Datum: 2017-09-28
Tid: 13:00
Lokal: EC, Hörsalsvägen 11, Göteborg
Opponent: Associate Professor Robin Strand (1) Centre for Image Analysis, Division of Visual Information and Interaction, Dept. of Information Technology, Uppsala University (2) Section of Radiology, Dept. of Surgical Sciences, Uppsala University